原文:Generative Adversarial Networks (GANs) are a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
原文:We evaluate the quality of samples quantitatively using two measures: the likelihood of the test data under the model, and the quality of the samples generated by the model.
结论:通过查看论文的图表和实验结果,可以了解GANs生成的图像质量和效果,并可以评价模型的优劣。
3. 研究论文的方法和算法
原文:The generator tries to produce data that come from some probability distribution, while the discriminator tries to distinguish between the generator’s samples and the real data.
原文:GANs can generate samples that are difficult to distinguish from the training data, and they can also generate new samples that are diverse and interesting.